Hugging Faceをスクレイピングする方法：完全技術ガイド

from playwright.sync_api import sync_playwright

def scrape_hf():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://huggingface.co/models')
        # Wait for model list to render
        page.wait_for_selector('article')
        models = page.query_selector_all('article h4')
        for m in models:
            print(m.inner_text())
        browser.close()

scrape_hf()

import scrapy

class HuggingFaceSpider(scrapy.Spider):
    name = 'hf_spider'
    start_urls = ['https://huggingface.co/models']

    def parse(self, response):
        for model in response.css('article'):
            yield {
                'title': model.css('h4::text').get(),
                'author': model.css('span.text-gray-400::text').get()
            }
        # Handle pagination
        next_page = response.css('a[aria-label="Next"]::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
    const browser = await puppeteer.launch();
    const page = await browser.newPage();
    await page.goto('https://huggingface.co/models');
    // Wait for the dynamic content to load
    await page.waitForSelector('article');
    const data = await page.evaluate(() => {
        return Array.from(document.querySelectorAll('article h4')).map(h => h.innerText);
    });
    console.log(data);
    await browser.close();
})();